e-Empowerment of young adults with special needs Behind the computer screen I am not disabled

Shpigelman, Carmit‐Noa; Weiss, Patrice L.; Reiter, Shunit

doi:10.1109/icvr.2009.5174207

Cited by 1 publication

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Home assistants are employed in different situations such as helping elderly people, people with special needs (Shpigelman et al, 2009), and improving educational processes. Furthermore, in rural areas in which access is limited by distance, isolation and lack of transportation, the usage of home assistants can provide medical evaluation and intervention, and enhance quality of life (Hudson and Cohen, 2006).…”

Section: The Authors Presented An Intelligentmentioning

confidence: 99%

“…Furthermore, in rural areas in which access is limited by distance, isolation and lack of transportation, the usage of home assistants can provide medical evaluation and intervention, and enhance quality of life (Hudson and Cohen, 2006). Computer-mediated support interventions for people with special needs have been proved to provide socio-emotional support for those with needs (Shpigelman et al, 2009), so the home assistants may also help promote this inclusion. IPAs can also act as a teacher, learning facilitator or a student peer in collaborative setting, for education.…”

Section: The Authors Presented An Intelligentmentioning

confidence: 99%

See 1 more Smart Citation

Optimisation of phonetic aware speech recognition through multi-objective evolutionary algorithms

Bird

Wanner

Ekárt

et al. 2020

Expert Systems with Applications

View full text Add to dashboard Cite

Recent advances in the availability of computational resources allow for more sophisticated approaches to speech recognition than ever before. This study considers Artificial Neural Network and Hidden Markov Model methods of classification for Human Speech Recognition through Diphthong Vowel sounds in the English Phonetic Alphabet rather than the classical approach of the classification of whole words and phrases, with a specific focus on both single and multi-objective evolutionary optimisation of bioinspired classification methods. A set of audio clips are recorded by subjects from the United Kingdom and Mexico and the recordings are transformed into a static dataset of statistics by way of their Mel-Frequency Cepstral Coefficients (MFCC) at sliding window length of 200ms as well as a reshaped MFCC timeseries format for forecast-based models. An deep neural network with evolutionary optimised topology achieves 90.77% phoneme classification accuracy in comparison to the best HMM that achieves 86.23% accuracy with 150 hidden units, when only accuracy is considered in a single-objective optimisation approach. The obtained solutions are far more complex than the HMM taking around 248 seconds to train on powerful hardware versus 160 for the HMM. A multi-objective approach is explored due to this. In the multiobjective approaches of scalarisation presented, within which real-time resource usage is also considered towards solution fitness, far more optimal

show abstract

Section: The Authors Presented An Intelligentmentioning

confidence: 99%

Section: The Authors Presented An Intelligentmentioning

confidence: 99%